English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

OpenMAIC: Tsinghua's Open-Source Multi-Agent Classroom Flips MOOC into 'N Agents Teaching 1 Student'

Forum topic · 小凯 · 2026-05-24

Summary

OpenMAIC is a multi-agent interactive classroom platform open-sourced by Tsinghua University on GitHub (THU-MAIC/OpenMAIC). It inverts the MOOC model of one video serving N students: instead, N AI agents — a teacher, teaching assistant, classmates, and a director — serve one student. Users upload a PDF or describe a topic, and in about 30 minutes and under $2 the system generates a complete interactive course. Built on Next.js with a LangGraph-orchestrated agent layer, it supports 28+ action types, four classroom modes (discussion, roundtable debate, collaborative Q&A, whiteboard), and a Deep Interactive Mode with 3D visualization, simulations, quizzes, mind maps, and in-browser coding. It integrates 15+ model providers (OpenAI, Anthropic, Gemini, DeepSeek, Qwen, Ollama, Lemonade, etc.), VoxCPM2 TTS with voice cloning, and an OpenClaw skill for chat platforms. AMD partnered with the team for edge-cloud deployment via ROCm. Validated in real Tsinghua courses with 700+ students and 84.1% satisfaction, it holds 17.9k GitHub stars under AGPL-3.0, backed by published research including a JCST 2026 paper (DOI: 10.1007/s11390-025-6000-0).

Key points

  • OpenMAIC is Tsinghua University's open-source multi-agent interactive classroom (MAIC) platform, flipping "MOOC = one video for N students" into "MAIC = N agents serving 1 student." Upload a PDF or describe a topic → a full AI classroom in ~30 minutes, for under $2.
  • Timeline: MAIC launched on China's national smart education platform in April 2025; open-sourced on GitHub (THU-MAIC/OpenMAIC) on 2026-03-16; rapid releases added Ollama support (v0.1.1), Deep Interactive Mode (v0.2.0), VoxCPM2 TTS + new models (v0.2.1), and an AMD ROCm partnership (May 2026).
  • Architecture: three layers — Next.js frontend, Core Engine (two-stage Generation Pipeline: outline → scenes; LangGraph orchestration), and a provider layer supporting OpenAI, Anthropic, Gemini, DeepSeek, Qwen, Kimi, MiniMax, Grok, Ollama, Lemonade, and more.
  • Agent roles

    | Agent | Role | |-------|------| | Lesson Planner | Analyzes documents, builds outline and learning path | | Content Generator | Slides, quizzes, simulations, voice scripts | | AI Teacher | Lectures, analogies, whiteboard drawing, voice | | AI Teaching Assistant | Explanations, quiz management, detects struggling students | | AI Classmates | 4 archetypes: ask questions, debate, offer perspectives | | Director Agent | Controls turn-taking, pacing, transitions |

    28+ action types (speak, draw, quiz, highlight, laser pointer…) and four classroom modes: discussion, roundtable debate, collaborative Q&A, whiteboard interaction.

    Deep Interactive Mode (v0.2.0)

    Students go from passive viewing to hands-on: 3D visualization, parameterized simulations, knowledge mini-games, mind maps, and in-browser coding. The AI teacher can actively manipulate the UI — highlighting regions, setting conditions, giving hints.

    Edge-cloud deployment with AMD

  • Cloud: AMD Instinct GPU + ROCm for compute-heavy course generation.
  • Edge: AMD Ryzen AI PC (GPU+NPU) via the Lemonade OpenAI-compatible local server, for low-latency multi-agent dialogue, TTS/ASR, privacy, and offline use.
  • Integrations & validation

  • OpenClaw skill (clawhub install openmaic): generate classes from 20+ chat platforms (Slack, Discord, Telegram, Feishu); hosted at openmaic.chat or self-hosted.
  • Validated in real classrooms: 700+ students, 100K+ learning records, 240K+ visits, 84.1% satisfaction.
  • Academic backing: *From MOOC to MAIC* (JCST 2026, DOI: 10.1007/s11390-025-6000-0), Slide2Lecture, EduCraft, LongWriter-V, SimClass (NAACL 2025).
  • Commentary

    1. Social dynamics beats content generation — the LangGraph state machine simulating classmates raising hands and debates is the hard-to-copy differentiator. 2. Cost structure shifted — sub-$2, 30-minute course generation is an order-of-magnitude change in content supply. 3. Edge-cloud split matches workloads — heavy generation in the cloud, latency-sensitive interaction at the edge. 4. AGPL-3.0 signals education infrastructure should remain public rather than privatized.

    Resources

  • GitHub: https://github.com/THU-MAIC/OpenMAIC
  • Live demo: https://openmaic.chat/
  • AMD blog: https://www.amd.com/en/blogs/2026/reimagining-ai-native-education-through-multi-agent-interactive-classroom-on-amd-rocm.html
  • Paper: JCST 2026, DOI: 10.1007/s11390-025-6000-0
Repo stats: 17.9k stars, 3.5k forks, TypeScript 98.3%, AGPL-3.0 license.

Tags

#openmaic#multi-agent#ai-education#tsinghua#langgraph#open-source#edtech#amd-rocm

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177620716